RESUMEN
RATIONALE AND OBJECTIVES: Given the high volume of chest radiographs, radiologists frequently encounter heavy workloads. In outpatient imaging, a substantial portion of chest radiographs show no actionable findings. Automatically identifying these cases could improve efficiency by facilitating shorter reading workflows. PURPOSE: A large-scale study to assess the performance of AI on identifying chest radiographs with no actionable disease (NAD) in an outpatient imaging population using comprehensive, objective, and reproducible criteria for NAD. MATERIALS AND METHODS: The independent validation study includes 15000 patients with chest radiographs in posterior-anterior (PA) and lateral projections from an outpatient imaging center in the United States. Ground truth was established by reviewing CXR reports and classifying cases as NAD or actionable disease (AD). The NAD definition includes completely normal chest radiographs and radiographs with well-defined non-actionable findings. The AI NAD Analyzer1 (trained with 100 million multimodal images and fine-tuned on 1.3 million radiographs) utilizes a tandem system with image-level rule in and compartment-level rule out to provide case level output as NAD or potential actionable disease (PAD). RESULTS: A total of 14057 cases met our eligibility criteria (age 56 ± 16.1 years, 55% women and 45% men). The prevalence of NAD cases in the study population was 70.7%. The AI NAD Analyzer correctly classified NAD cases with a sensitivity of 29.1% and a yield of 20.6%. The specificity was 98.9% which corresponds to a miss rate of 0.3% of cases. Significant findings were missed in 0.06% of cases, while no cases with critical findings were missed by AI. CONCLUSION: In an outpatient population, AI can identify 20% of chest radiographs as NAD with a very low rate of missed findings. These cases could potentially be read using a streamlined protocol, thus improving efficiency and consequently reducing daily workload for radiologists.
RESUMEN
Chest radiography (CXR) continues to be the most frequently performed imaging examination worldwide, yet it remains prone to frequent errors in interpretation. These pose potential adverse consequences to patients and are a leading motivation for medical malpractice lawsuits. Commonly missed CXR findings and the principal causes of these errors are reviewed and illustrated. Perceptual errors are the predominant source of these missed findings. The medicolegal implications of such errors are explained. Awareness of commonly missed CXR findings, their causes, and their consequences are important in developing approaches to reduce and mitigate these errors.
Asunto(s)
Servicio de Urgencia en Hospital , Radiografía Torácica , Humanos , Radiografía Torácica/métodos , Radiografía , Estudios RetrospectivosRESUMEN
Chest radiography (CXR), the most frequently performed imaging examination, is vulnerable to interpretation errors resulting from commonly missed findings. Methods to reduce these errors are presented. A practical approach using a systematic and comprehensive visual search strategy is described. The use of a checklist for quality control in the interpretation of CXR images is proposed to avoid overlooking commonly missed findings of clinical importance. Artificial intelligence is among the emerging and promising methods to enhance detection of CXR abnormalities. Despite their potential adverse consequences, errors offer opportunities for continued education and quality improvements in patient care, if managed within a just, supportive culture.
Asunto(s)
Inteligencia Artificial , Radiografía Torácica , Humanos , Radiografía Torácica/métodos , RadiografíaRESUMEN
Purpose: Rapid prognostication of COVID-19 patients is important for efficient resource allocation. We evaluated the relative prognostic value of baseline clinical variables (CVs), quantitative human-read chest CT (qCT), and AI-read chest radiograph (qCXR) airspace disease (AD) in predicting severe COVID-19. Approach: We retrospectively selected 131 COVID-19 patients (SARS-CoV-2 positive, March to October, 2020) at a tertiary hospital in the United States, who underwent chest CT and CXR within 48 hr of initial presentation. CVs included patient demographics and laboratory values; imaging variables included qCT volumetric percentage AD (POv) and qCXR area-based percentage AD (POa), assessed by a deep convolutional neural network. Our prognostic outcome was need for ICU admission. We compared the performance of three logistic regression models: using CVs known to be associated with prognosis (model I), using a dimension-reduced set of best predictor variables (model II), and using only age and AD (model III). Results: 60/131 patients required ICU admission, whereas 71/131 did not. Model I performed the poorest ( AUC = 0.67 [0.58 to 0.76]; accuracy = 77 % ). Model II performed the best ( AUC = 0.78 [0.71 to 0.86]; accuracy = 81 % ). Model III was equivalent ( AUC = 0.75 [0.67 to 0.84]; accuracy = 80 % ). Both models II and III outperformed model I ( AUC difference = 0.11 [0.02 to 0.19], p = 0.01 ; AUC difference = 0.08 [0.01 to 0.15], p = 0.04 , respectively). Model II and III results did not change significantly when POv was replaced by POa. Conclusions: Severe COVID-19 can be predicted using only age and quantitative AD imaging metrics at initial diagnosis, which outperform the set of CVs. Moreover, AI-read qCXR can replace qCT metrics without loss of prognostic performance, promising more resource-efficient prognostication.
RESUMEN
Pulmonary functional imaging may be defined as the regional quantification of lung function by using primarily CT, MRI, and nuclear medicine techniques. The distribution of pulmonary physiologic parameters, including ventilation, perfusion, gas exchange, and biomechanics, can be noninvasively mapped and measured throughout the lungs. This information is not accessible by using conventional pulmonary function tests, which measure total lung function without viewing the regional distribution. The latter is important because of the heterogeneous distribution of virtually all lung disorders. Moreover, techniques such as hyperpolarized xenon 129 and helium 3 MRI can probe lung physiologic structure and microstructure at the level of the alveolar-air and alveolar-red blood cell interface, which is well beyond the spatial resolution of other clinical methods. The opportunities, challenges, and current stage of clinical deployment of pulmonary functional imaging are reviewed, including applications to chronic obstructive pulmonary disease, asthma, interstitial lung disease, pulmonary embolism, and pulmonary hypertension. Among the challenges to the deployment of pulmonary functional imaging in routine clinical practice are the need for further validation, establishment of normal values, standardization of imaging acquisition and analysis, and evidence of patient outcomes benefit. When these challenges are addressed, it is anticipated that pulmonary functional imaging will have an expanding role in the evaluation and management of patients with lung disease.
Asunto(s)
Enfermedades Pulmonares/diagnóstico por imagen , Enfermedades Pulmonares/fisiopatología , Medios de Contraste , Diagnóstico Precoz , Humanos , Aumento de la Imagen/métodos , Interpretación de Imagen Asistida por Computador/métodos , Mejoramiento de la Calidad , Pruebas de Función RespiratoriaRESUMEN
Over the past few decades, pulmonary imaging technologies have advanced from chest radiography and nuclear medicine methods to high-spatial-resolution or low-dose chest CT and MRI. It is currently possible to identify and measure pulmonary pathologic changes before these are obvious even to patients or depicted on conventional morphologic images. Here, key technological advances are described, including multiparametric CT image processing methods, inhaled hyperpolarized and fluorinated gas MRI, and four-dimensional free-breathing CT and MRI methods to measure regional ventilation, perfusion, gas exchange, and biomechanics. The basic anatomic and physiologic underpinnings of these pulmonary functional imaging techniques are explained. In addition, advances in image analysis and computational and artificial intelligence (machine learning) methods pertinent to functional lung imaging are discussed. The clinical applications of pulmonary functional imaging, including both the opportunities and challenges for clinical translation and deployment, will be discussed in part 2 of this review. Given the technical advances in these sophisticated imaging methods and the wealth of information they can provide, it is anticipated that pulmonary functional imaging will be increasingly used in the care of patients with lung disease. © RSNA, 2021 Online supplemental material is available for this article.
Asunto(s)
Enfermedades Pulmonares/diagnóstico por imagen , Enfermedades Pulmonares/fisiopatología , Imagen por Resonancia Magnética/métodos , Tomografía Computarizada por Rayos X/métodos , Inteligencia Artificial , Medios de Contraste , Humanos , Aumento de la Imagen/métodos , Interpretación de Imagen Asistida por Computador/métodos , Pruebas de Función RespiratoriaRESUMEN
OBJECTIVES: The aim of this study was to leverage volumetric quantification of airspace disease (AD) derived from a superior modality (computed tomography [CT]) serving as ground truth, projected onto digitally reconstructed radiographs (DRRs) to (1) train a convolutional neural network (CNN) to quantify AD on paired chest radiographs (CXRs) and CTs, and (2) compare the DRR-trained CNN to expert human readers in the CXR evaluation of patients with confirmed COVID-19. MATERIALS AND METHODS: We retrospectively selected a cohort of 86 COVID-19 patients (with positive reverse transcriptase-polymerase chain reaction test results) from March to May 2020 at a tertiary hospital in the northeastern United States, who underwent chest CT and CXR within 48 hours. The ground-truth volumetric percentage of COVID-19-related AD (POv) was established by manual AD segmentation on CT. The resulting 3-dimensional masks were projected into 2-dimensional anterior-posterior DRR to compute area-based AD percentage (POa). A CNN was trained with DRR images generated from a larger-scale CT dataset of COVID-19 and non-COVID-19 patients, automatically segmenting lungs, AD, and quantifying POa on CXR. The CNN POa results were compared with POa quantified on CXR by 2 expert readers and to the POv ground truth, by computing correlations and mean absolute errors. RESULTS: Bootstrap mean absolute error and correlations between POa and POv were 11.98% (11.05%-12.47%) and 0.77 (0.70-0.82) for average of expert readers and 9.56% to 9.78% (8.83%-10.22%) and 0.78 to 0.81 (0.73-0.85) for the CNN, respectively. CONCLUSIONS: Our CNN trained with DRR using CT-derived airspace quantification achieved expert radiologist level of accuracy in the quantification of AD on CXR in patients with positive reverse transcriptase-polymerase chain reaction test results for COVID-19.
Asunto(s)
COVID-19/diagnóstico por imagen , Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador/métodos , Radiografía Torácica , Radiólogos , Tomografía Computarizada por Rayos X , Estudios de Cohortes , Humanos , Pulmón/diagnóstico por imagen , Masculino , Estudios RetrospectivosRESUMEN
Pulmonary MRI provides structural and quantitative functional images of the lungs without ionizing radiation, but it has had limited clinical use due to low signal intensity from the lung parenchyma. The lack of radiation makes pulmonary MRI an ideal modality for pediatric examinations, pregnant women, and patients requiring serial and longitudinal follow-up. Fortunately, recent MRI techniques, including ultrashort echo time and zero echo time, are expanding clinical opportunities for pulmonary MRI. With the use of multicoil parallel acquisitions and acceleration methods, these techniques make pulmonary MRI practical for evaluating lung parenchymal and pulmonary vascular diseases. The purpose of this Fleischner Society position paper is to familiarize radiologists and other interested clinicians with these advances in pulmonary MRI and to stratify the Society recommendations for the clinical use of pulmonary MRI into three categories: (a) suggested for current clinical use, (b) promising but requiring further validation or regulatory approval, and (c) appropriate for research investigations. This position paper also provides recommendations for vendors and infrastructure, identifies methods for hypothesis-driven research, and suggests opportunities for prospective, randomized multicenter trials to investigate and validate lung MRI methods.
Asunto(s)
Enfermedades Pulmonares/diagnóstico por imagen , Imagen por Resonancia Magnética/métodos , Humanos , Aumento de la Imagen/métodos , Interpretación de Imagen Asistida por Computador/métodos , Selección de PacienteRESUMEN
Deep learning is a genre of machine learning that allows computational models to learn representations of data with multiple levels of abstraction using numerous processing layers. A distinctive feature of deep learning, compared with conventional machine learning methods, is that it can generate appropriate models for tasks directly from the raw data, removing the need for human-led feature extraction. Medical images are particularly suited for deep learning applications. Deep learning techniques have already demonstrated high performance in the detection of diabetic retinopathy on fundoscopic images and metastatic breast cancer cells on pathologic images. In radiology, deep learning has the opportunity to provide improved accuracy of image interpretation and diagnosis. Many groups are exploring the possibility of using deep learning-based applications to solve unmet clinical needs. In chest imaging, there has been a large effort to develop and apply computer-aided detection systems for the detection of lung nodules on chest radiographs and chest computed tomography. The essential limitation to computer-aided detection is an inability to learn from new information. To overcome these deficiencies, many groups have turned to deep learning approaches with promising results. In addition to nodule detection, interstitial lung disease recognition, lesion segmentation, diagnosis and patient outcomes have been addressed by deep learning approaches. The purpose of this review article was to cover the current state of the art for deep learning approaches and its limitations, and some of the potential impact on the field of radiology, with specific reference to chest imaging.
Asunto(s)
Aprendizaje Profundo , Enfermedades Pulmonares/diagnóstico por imagen , Radiografía Torácica/métodos , Tomografía Computarizada por Rayos X/métodos , Humanos , Pulmón/diagnóstico por imagenRESUMEN
BACKGROUND: Cross-sectional imaging of malignant pleural mesothelioma (MPM) can underestimate the presence of local tumor invasion. Since accurate staging is vital optimal choice of therapy, techniques that optimize pleural imaging are needed. Here we estimate the optimal timing of MPM enhancement on magnetic resonance imaging (MRI). METHODS: All MPM patients with intravenous (IV) contrast enhanced staging MRI between 2000-2016 at our institution were retrospectively selected for image analysis. Patients with incomplete imaging protocol and maximum pleural tumor thickness <1 cm were excluded. Quantitative measurements of tumor signal intensity were obtained on pre-contrast and post-contrast phases where MRI acquisition parameters were fixed. Using best-fit model curves, predicted maximum time points of enhancement were determined using a simulation of predicted values. Additionally, a qualitative assessment of tumor conspicuity was performed at all IV contrast time delays imaged. A statistical analysis assessed for correlation between qualitative lesion conspicuity and quantitative tumor enhancement. RESULTS: Of the 42 MPM patients who had undergone staging MRI during the study period, 12 patients met the study criteria. Peak tumor enhancement was between 150 and 300 sec following IV contrast administration. Within this time window, 80% of patients are projected to have reached >80%, >85%, and >90% peak tumor enhancement. There was a statistically significant correlation between increasing tumor enhancement and subjective lesion conspicuity. CONCLUSIONS: Optimal MPM enhancement on MRI likely occurs at a time delay between 2.5-5 min following IV contrast administration. Further study of delayed phase enhancement of MPM with dynamic contrast enhanced MRI is warranted.
RESUMEN
Purpose To assess the feasibility and optimize the accuracy of the multibreath wash-in hyperpolarized helium 3 ((3)He) approach to ventilation measurement by using magnetic resonance (MR) imaging as well as to examine the physiologic differences that this approach reveals among nonsmokers, asymptomatic smokers, and patients with chronic obstructive pulmonary disease (COPD). Materials and Methods All experiments were approved by the local institutional review board and compliant with HIPAA. Informed consent was obtained from all subjects. To measure fractional ventilation, the authors administered a series of identical normoxic hyperpolarized gas breaths to the subject; after each inspiration, an image was acquired during a short breath hold. Signal intensity buildup was fit to a recursive model that regionally solves for fractional ventilation. This measurement was successfully performed in nine subjects: three healthy nonsmokers (one man, two women; mean age, 45 years ± 4), three asymptomatic smokers (three men; mean age, 51 years ± 5), and three patients with COPD (three men; mean age, 59 years ± 5). Repeated measures analysis of variance was performed, followed by post hoc tests with Bonferroni correction, to assess the differences among the three cohorts. Results Whole-lung fractional ventilation as measured with hyperpolarized (3)He in all subjects (mean, 0.24 ± 0.06) showed a strong correlation with global fractional ventilation as measured with a gas delivery device (R(2) = 0.96, P < .001). Significant differences between the means of whole-lung fractional ventilation (F2,10 = 7.144, P = .012) and fractional ventilation heterogeneity (F2,10 = 7.639, P = .010) were detected among cohorts. In patients with COPD, the protocol revealed regions wherein fractional ventilation varied substantially over multiple breaths. Conclusion Multibreath wash-in hyperpolarized (3)He MR imaging of fractional ventilation is feasible in human subjects and demonstrates very good global (whole-lung) precision. Fractional ventilation measurement with this physiologically realistic approach reveals significant differences between patients with COPD and healthy subjects. To minimize error, several sources of potential bias must be corrected when calculating fractional ventilation. (©) RSNA, 2016 Online supplemental material is available for this article.
Asunto(s)
Helio/administración & dosificación , Procesamiento de Imagen Asistido por Computador/métodos , Pulmón/diagnóstico por imagen , Imagen por Resonancia Magnética/métodos , Enfermedad Pulmonar Obstructiva Crónica/diagnóstico por imagen , Fumar/fisiopatología , Adulto , Biomarcadores/análisis , Estudios de Casos y Controles , Estudios de Factibilidad , Femenino , Helio/análisis , Humanos , Pulmón/fisiología , Masculino , Persona de Mediana Edad , Enfermedad Pulmonar Obstructiva Crónica/fisiopatología , Procesamiento de Señales Asistido por ComputadorRESUMEN
PURPOSE: The aim of the study was to evaluate opinions and perceptions of radiologists and referring practitioners regarding reports of portable chest radiography (pCXR) obtained in the intensive care unit (ICU). MATERIALS AND METHODS: A total of 1265 referring practitioners and 76 radiologists were invited to participate in 2 internet-based surveys, containing 15 and 17 multiple choice questions, respectively, similarly presented to both groups, utilizing a Likert scale or multiple choices. Results were compared using the Fisher exact test or χ test. RESULTS: One hundred ninety-two referring practitioners and 63 radiologists answered the surveys, resulting in response rates of 15% and 83%. The majority of radiologists and referring practitioners are satisfied with the quality of the reports; however, radiologists and referring practitioners disagree about the reports' clinical value and impact, the referring practitioners having a more positive view. Both groups overwhelmingly agree that pertinent clinical information is crucial for optimal image interpretation. The 2 groups differ in their preferences regarding report style and information content, with radiologists strongly supporting concise reports emphasizing temporal changes and major findings, whereas referring practitioners prefer more complete, itemized structured reports describing support devices in detail. CONCLUSIONS: The results substantiate the perceived clinical value of radiologist reports for pCXR, from the perspective of referring practitioners. Nonetheless, there is disagreement regarding report structure and content. Several issues were raised, offering opportunities for improvement, which may increase referring practitioners' satisfaction and positively impact patient outcomes. Any strategy to implement standardized structured reports for pCXR will have to satisfy referring practitioners' needs while optimizing radiologists' efficiency, will have to be widely accepted, and will have to fulfill the overarching goal of maximizing the value of pCXR reports.
Asunto(s)
Actitud del Personal de Salud , Unidades de Cuidados Intensivos , Registros Médicos/normas , Sistemas de Atención de Punto , Radiografía Torácica , Humanos , Derivación y Consulta , Reproducibilidad de los ResultadosRESUMEN
PURPOSE: To determine whether hyperpolarized helium 3 magnetic resonance (MR) imaging to measure alveolar partial pressure of oxygen (Pao2) shows sufficient test-retest repeatability and between-cohort differences to be used as a reliable technique for detection of alterations in gas exchange in asymptomatic smokers. MATERIALS AND METHODS: The protocol was approved by the local institutional review board and was HIPAA compliant. Informed consent was obtained from all subjects. Two sets of MR images were obtained 10 minutes apart in 25 subjects: 10 nonsmokers (five men, five women; mean ± standard deviation age, 50 years ± 6) and 15 smokers (seven women, eight men; mean age, 50 years ± 8). A mixed-effects model was developed to identify the regional repeatability of Pao2 measurements as an intraclass correlation coefficient. Ten smokers were matched with the 10 nonsmokers on the basis of signal-to-noise ratio (SNR). Three separate models were generated: one for nonsmokers, one for the SNR-matched smokers, and one for the five remaining smokers, who were imaged with a significantly higher SNR. RESULTS: Short-term back-to-back regional reproducibility was assessed by using intraclass correlation coefficients, which were 0.67 and 0.65 for SNR case-matched nonsmokers and smokers, respectively. Repeatability was a strong function of SNR; a 50% increase in SNR in the remaining smokers improved the intraclass correlation coefficient to 0.82. Although repeatability was not significantly different between the SNR-matched cohorts (P = .44), the smoker group showed higher spatial and temporal variability in Pao2. CONCLUSION: The short-term test-retest repeatability of hyperpolarized gas MR imaging of regional Pao2 was good. Asymptomatic smokers exhibited greater spatial and temporal variability in Pao2 than did the nonsmokers, which suggests that this parameter allows detection of small functional alterations associated with smoking.
Asunto(s)
Imagen por Resonancia Magnética/métodos , Intercambio Gaseoso Pulmonar , Fumar/fisiopatología , Adulto , Femenino , Helio , Humanos , Isótopos , Masculino , Persona de Mediana Edad , Oxígeno , Presión Parcial , Alveolos Pulmonares , Reproducibilidad de los Resultados , Factores de TiempoRESUMEN
PURPOSE: To assess the ability of helium 3 ((3)He) magnetic resonance (MR) imaging of regional alveolar partial pressure of oxygen (Pao2) to depict smoking-induced functional alterations and to compare its efficacy to that of current diagnostic techniques. MATERIALS AND METHODS: This study was approved by the local institutional review board and was compliant with HIPAA. All subjects provided informed consent. A total of 43 subjects were separated into three groups: nonsmokers, asymptomatic smokers, and symptomatic smokers. All subjects underwent a Pao2 imaging session followed by clinically standard pulmonary function tests (PFTs), the 6-minute walk test, and St George Respiratory Questionnaire (SGRQ). The whole-lung mean and standard deviation of Pao2 were compared with metrics derived from PFTs, the 6-minute walk test, and the SGRQ. A logistic regression model was developed to identify the predictors of alterations to the lungs of asymptomatic smokers. RESULTS: The whole-lung standard deviation of Pao2 correlated with PFT metrics (forced expiratory volume in 1 second [FEV1]/forced vital capacity [FVC], Pearson r = -0.69, P < .001; percentage predicted FEV1, Pearson r = -0.67, P < .001; diffusing capacity of lung for carbon monoxide [Dlco], Pearson r = -0.45, P = .003), SGRQ score (Pearson r = 0.67, P < .001), and distance walked in 6 minutes (Pearson r = -0.47, P = .002). The standard deviation of Pao2 was significantly higher in asymptomatic smokers than in nonsmokers (change in the standard deviation of Pao2 = 7.59 mm Hg, P = .041) and lower when compared with symptomatic smokers (change in the standard deviation of Pao2 = 10.72 mm Hg, P = .001). A multivariate prediction model containing FEV1/FVC and the standard deviation of Pao2 (as significant predictors of subclinical changes in smokers) and Dlco (as a confounding variable) was formulated. This model resulted in an area under the receiver operating characteristic curve with a significant increase of 29.2% when compared with a prediction model based solely on nonimaging clinical tests. CONCLUSION: The (3)He MR imaging heterogeneity metric (standard deviation of Pao2) enabled the differentiation of all three study cohorts, which indicates that it can depict smoking-related functional alterations in asymptomatic current smokers.
Asunto(s)
Helio , Imagen por Resonancia Magnética/métodos , Oxígeno/fisiología , Alveolos Pulmonares/fisiopatología , Fumar/fisiopatología , Femenino , Humanos , Isótopos , Masculino , Persona de Mediana Edad , Presión Parcial , Pruebas de Función RespiratoriaRESUMEN
OBJECTIVE: The purpose of this review is to describe classification schemes and imaging findings in the diagnosis and management of pulmonary hypertension. CONCLUSION: Pulmonary hypertension is a complex pathophysiologic condition in which several clinical entities increase pressure in the pulmonary circulation, progressively impairing cardiopulmonary function and, if untreated, causing right ventricular failure. Current classification schemes emphasize the necessity of an early, accurate etiologic diagnosis for a tailored therapeutic approach. Imaging plays an increasingly important role in the diagnosis and management of suspected pulmonary hypertension.